Noometry

Model comparison

GPT-5.4 mini vs Llama 3-8B

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 25.5 on the Noometry Index.

Last verified . 23 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Llama 3-8B Meta

25.5

Rank #344 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 7.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for GPT-5.4 mini and 1.9% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniLlama 3-8B
ProviderOpenAIMeta
Noometry Index45.025.5
Released2026-03-172024-04-18
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4634

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.2 (#72), Llama 3-8B: 31.0 (#289)

BenchmarkGPT-5.4 miniLlama 3-8B
LMArena Coding14381152
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
BigCodeBench Instruct—31.9%
BigCodeBench Complete—36.9%
ALE-Bench1,189—
HumanEval+—56.7%
MBPP+—54.8%

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.9 (#81), Llama 3-8B: —

BenchmarkGPT-5.4 miniLlama 3-8B
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Llama 3-8B: 14.3 (#326)

BenchmarkGPT-5.4 miniLlama 3-8B
Chess Puzzles24%0%
LMArena Hard Prompts14241133
DTBench80%43.9%
Epoch Capabilities Index148.84116.45
ForecastBench5758.6
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Thematic Generalization61.7%—
Mystery Game Puzzles11%—
LMCA40.8%—
Adversarial NLI—57.3%
WinoGrande—75.7%

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), Llama 3-8B: 8.8 (#323)

BenchmarkGPT-5.4 miniLlama 3-8B
OTIS Mock AIME 2024-202588.9%1.9%
LMArena Math14191151
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
ProofBench21%—
MATH Level 5—6.1%
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.5 (#67), Llama 3-8B: 7.8 (#308)

BenchmarkGPT-5.4 miniLlama 3-8B
GPQA Diamond86.9%26.1%
LMArena Expert14351113
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), Llama 3-8B: —

BenchmarkGPT-5.4 miniLlama 3-8B
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 51.9 (#96), Llama 3-8B: 30.8 (#261)

BenchmarkGPT-5.4 miniLlama 3-8B
LMArena Non-English14051098
LMArena Chinese14461076
LMArena French14401159
LMArena German14091104
LMArena Japanese1374967
LMArena Korean13681004
LMArena Russian14171109
LMArena Spanish14051173

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.1 (#102), Llama 3-8B: 58.4 (#260)

BenchmarkGPT-5.4 miniLlama 3-8B
LMArena Instruction Following14051127

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 43.0 (#112), Llama 3-8B: 34.2 (#251)

BenchmarkGPT-5.4 miniLlama 3-8B
LMArena Longer Query14071128

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), Llama 3-8B: 37.5 (#256)

BenchmarkGPT-5.4 miniLlama 3-8B
LMArena Text14121166
LMArena Creative Writing13701150
LMArena Multi-Turn14291152
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Llama 3-8B?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 25.5 on the Noometry Index.

Is GPT-5.4 mini or Llama 3-8B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 31.0 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and Llama 3-8B share?

23 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper